gemini-3.5-thinking

gemini-3.5-thinking by Google (Gemini) is optimized for image generation/editing workflows. Contracts follow ToAPIs docs for production-ready API integration.

モデルタイプ：

料金： Input 90 クレジット/1M, Output 540 クレジット/1M

Set chat parameters

System Prompt

Advanced options

Example params

Temperature最大トークン

Request preview

{
  "model": "gemini-3.5-thinking",
  "messages": [
    {
      "role": "system",
      "content": "You are a precise, direct AI assistant that is strong at engineering decomposition."
    },
    {
      "role": "user",
      "content": "Use gemini-3.5-thinking to break a complex product requirement into actionable engineering tasks."
    }
  ],
  "stream": true,
  "max_tokens": 4096,
  "temperature": 0.7
}

View API Docs

Type a message to test the model.

生成例

gemini-3.5-thinking の生成結果を見る

このモデルで生成

gemini-3.5-thinking #1

透明な料金体系

gemini-3.5-thinking pricing

Text usage is billed by actual token consumption. Final billing follows the current account quote.

クレジットを追加

Input 90 クレジット/1M, Output 540 クレジット/1M

ToAPIs を選ぶ理由

Why call gemini-3.5-thinking through ToAPIs?

Keep model access, API keys, billing, and usage management in one workflow.

High-quality generation

Generate production-ready visual assets via a unified API.

Reference consistency

Use references to stabilize style and composition.

Parameter tuning

Tune ratio/count/sampling for quality and cost balance.

Connect in three steps

Create a key, send a compatible chat request, and monitor usage.

1
Step 1
Set Authorization: Bearer <YOUR_API_KEY>.
2
Step 2
Call image generation endpoint with model, prompt, and size.
3
Step 3
Optionally pass reference_images for stronger consistency.

When to use gemini-3.5-thinking

Use case 1

When generating marketing, e-commerce, and social visual assets quickly.

Use case 2

When reference-guided consistency is required.

よくある質問

gemini-3.5-thinking FAQ

What is gemini-3.5-thinking best for?

Best for high-frequency creative generation and reference-guided consistency workflows.

Image or video model error: invalid apitype: -1

This usually means the request was sent to the wrong endpoint. Image and video models typically do not use the chat endpoint. Instead, submit the documented HTTP task request and poll the task status endpoint for results. Check the actual request code, URL, and payload first.

An image or video task failed, but the user was still charged

Ask the user for the task log or screenshot first and check whether input or output token usage appears. If token accounting shows up, the request was likely sent through a chat endpoint instead of the proper media workflow. Image and video models usually run as async HTTP task APIs: submit the task first, then poll by task id according to the relevant docs.

gemini-3.5-thinking API

Start building with gemini-3.5-thinking

Test a request here, then continue in the dashboard or API documentation.

Start for free View API Docs

Try gemini-3.5-thinking with one ToAPIs key.

Use the same account and API surface across supported text models.

Quick Answer

Key Parameters

Common Errors